Haoxin G. Email & Phone Number

Santa Clara, Ca, Us

San Jose, California, United States

- TikTok Shop&Search Monetization, Advertising PlatformMachine learning Model Input Feature Pipeline, including both offline and online feature extraction using Spark/SQL and Tensorflow Ops and computing graph.Highly available and scalable distributed global multi-datacenter setup, core microservices CI/CD, concurrent RPC network routing, cache strategy optimization, real time system monitoring dashboard and alarming, core system disaster recovery and backup- Search Ads Traffic Strategy OptimizationBuild Causal Forest Model to find the best personalized advertisement gap & estimated-cpm filtering threshold treatment for each individual user. Build ruled base User Strategy Groups, deploy different traffic strategies to protect new users from exposing overloaded ads or push more ads to high business value users.

Palo Alto, California, United States

Designed and built a next-generation Distributed ML Model Training Framework for the ad recommendation tasks. The platform handles >400 million user ad click events per day and real time serving 500B-parameter models.- Backend parts: HDFS-Kafka-Flink-ThriftServer input data streaming pipeline, Flatbuffer-gRPC distributed server communication, online model inference healthiness Monitoring, platform engineering metrics Monitoring, auto model quality validation.- ML parts: Distributed model parallelism & data parallelism architecture using TF Distributed Strategy, FTRL sparse optimizer using CUDA Programming, synchronized ML model Checkpointing, HBM-RAM-ParameterServer embedding storage caching architecture, FP16 mixed precision training

Greater New York City Area

- Yahoo Video AI Tagging Platform.The platform is serving CV, NLP, and ML models in dockerized K8S environments to finish tasks like speech recognition, celebrity detection, video sensitive content detection, named entity extraction, video categorization, etc.- NFL Football Field Detection & AR SystemIndividually researched and developed a football field computer vision segmentation model training and inference pipeline, including data augmentation, ICNet based neural network training, hyper-parameter tuning, model parameter validation, XLA compiler optimization and tflite model serving optimization.This work was patented in the US and integrated into NFL OnePass App, achieving 99% reliability in the 2020 Super Bowl LIV.

Ithaca, New York Area

Utilize ResBlock based 3D U-net and RPN/FPN to detect medical landmarks in the low dose CT images. Crop 3D image into 128*128*128 patches to fit one image into GPU's memory. Group norm technic is used between ResBlocks.

Beijing City, China

Master Of Engineering (M.Eng.), Electrical And Computer Engineering, Gpa 3.7

Activities and Societies: I am at Cornell Tech campus of Cornell University FYI: https://tech.cornell.edu

Bachelor Of Engineering (B.Eng.), Telecommunications Engineering, Major Gpa 3.7